Earth.com Scientists have now used artificial intelligence, computer systems that learn patterns from data, to write complete viral genomes from scratch in the lab.
In parallel, a Microsoft-led study showed that AI tools can redesign known toxins so they escape common DNA synthesis safety checks. Those AI-built viruses are bacteriophages, viruses that infect bacteria rather than humans, making them useful test cases but also vivid warnings.
Why experts fear AI viruses
The work revealing how AI-designed proteins can slip past genetic safety checks was led by Bruce J. Wittmann at Microsoft Research.
He works as a senior applied scientist, focusing on tools that make DNA screening more reliable for laboratories and synthesis companies.
These projects rely on genome-language models, AI tools that guess plausible stretches of DNA in a sequence.
Once trained on thousands of sequences, those models can suggest entirely new genomes that still resemble natural viral families.
That creative reach makes it harder for experts to anticipate how a machine-designed virus or protein might behave in real experiments.